© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 13391
    Prev
    Next
    INDEX
    Explanations

    r&b and urban music

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ведениÑı
    -0.20
    aments
    -0.18
     hem
    -0.18
     Hem
    -0.18
    为æŃ¢
    -0.17
    éĵ
    -0.17
    é½
    -0.17
    าà¸ĩ
    -0.17
    éĥ½æĥ³
    -0.17
    å¯Ĵ
    -0.17
    POSITIVE LOGITS
    人士
    0.20
    è¿ĩåİ»çļĦ
    0.20
    èĿĮ
    0.20
    ä¸īåįģå¹´
    0.19
     divor
    0.19
    ¿
    0.18
    æ§
    0.18
    纡
    0.18
    巨头
    0.18
    NewItem
    0.18
    Activations Density 0.004%

    No Known Activations